Machine Unlearning using a Multi-GAN based Model
This addresses the problem of efficiently removing specific data from trained models for privacy and compliance, though it appears incremental as it builds on existing GAN-based unlearning methods.
The paper tackles machine unlearning by proposing a multi-GAN approach that introduces synthetic data with inverted class labels for forget datasets and fine-tunes a pre-trained model, achieving state-of-the-art performance on the CIFAR-10 dataset as tested with Membership Inference Attacks.
This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data reorganization in which synthetic data using the GAN model is introduced with inverted class labels of the forget datasets, and ii) fine-tuning the pre-trained model. The GAN models consist of two pairs of generators and discriminators. The generator discriminator pairs generate synthetic data for the retain and forget datasets. Then, a pre-trained model is utilized to get the class labels of the synthetic datasets. The class labels of synthetic and original forget datasets are inverted. Finally, all combined datasets are used to fine-tune the pre-trained model to get the unlearned model. We have performed the experiments on the CIFAR-10 dataset and tested the unlearned models using Membership Inference Attacks (MIA). The inverted class labels procedure and synthetically generated data help to acquire valuable information that enables the model to outperform state-of-the-art models and other standard unlearning classifiers.